Including the SLICE-3D training dataset - 400,000 skin lesion image crops extracted from 3D TBP for skin cancer detection
The training and testing datasets were curated for the ISIC 2024 Challenge hosted on Kaggle during the Summer of 2024.
A dataset descriptor covering the SLICD-3D dataset was published in Scientific Data and is openly available at https://www.nature.com/articles/s41597-024-03743-w.
The datasets contains 15mm-by-15mm field-of-view cropped images, centered on distinct lesions, that were extracted from 3D total body photographs. The official training dataset for the challenge is the SLICE-3D Dataset: 400,000 skin lesion image crops extracted from 3D TBP for skin cancer detection. The official testing dataset contain tiles from a separate set of patients.
Datasets were curated by the International Skin Imaging Collaboration (ISIC) from images contributed from the following sources:
Dataset | Training Images and Input Attributes | Training Supplement | Training Ground Truth | Test Data | Test Ground Truth | License |
---|---|---|---|---|---|---|
SLICE-3D | Download (1.2GB) 401,059 JPEG images of skin lesion image crops extracted from 3D TBP with metadata entries of age, sex, general anatomic site, common patient identifier, clinical size, and various data fields from the TBP Lesion Visualizer*. | Download Supplemental Metadata (40MB) 401,059 metadata entries of attributes which may be useful for training cross-validation. | Download (7MB) 401,059 entries of gold standard lesion malignancy values. | Not Available | Not Available | CC-BY-NC |
SLICE-3D Permissive | Download (623MB) 217,477 JPEG images of skin lesion image crops extracted from 3D TBP with metadata entries of age, sex, general anatomic site, common patient identifier, clinical size, and various data from the TBP Lesion Visualizer*. | Download Supplemental Metadata (21MB) 217,477 metadata entries of attributes which may be useful for training cross-validation. | Download (4MB) 217,477 entries of gold standard lesion malignancy values. | Not Available | Not Available | CC-BY |
* D’Alessandro, B. “Methods and apparatus for identifying skin features of interest.” US Patent #11,164,670. (2021).
To comply with the attribution requirements of the CC-BY-NC license , the aggregate “SLICE-3D” data must be cited as:
International Skin Imaging Collaboration. SLICE-3D 2024 Challenge Dataset. International Skin Imaging Collaboration https://doi.org/10.34970/2024-slice-3d (2024).
Creative Commons Attribution-Non Commercial 4.0 International License.
The dataset was generated by the International Skin Imaging Collaboration (ISIC) and images are from the following sources: Hospital Clínic de Barcelona, Memorial Sloan Kettering Cancer Center, Hospital of Basel, FNQH Cairns, The University of Queensland, Melanoma Institute Australia, Monash University and Alfred Health, University of Athens Medical School, and Medical University of Vienna.
You should have received a copy of the license along with this work.
If not, see https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt .
To comply with the attribution requirements of the CC-BY license , the aggregate “SLICE-3D Permissive” data must be cited as:
International Skin Imaging Collaboration. SLICE-3D 2024 Permissive Challenge Dataset. International Skin Imaging Collaboration https://doi.org/10.34970/2024-slice-3d-permissive (2024).
Creative Commons Attribution 4.0 International License.
The dataset was generated by the International Skin Imaging Collaboration (ISIC) and images are from the following sources: Memorial Sloan Kettering Cancer Center, FNQH Cairns, The University of Queensland, Melanoma Institute Australia, and University of Athens Medical School.
You should have received a copy of the license along with this work.
If not, see https://creativecommons.org/licenses/by/4.0/legalcode.txt .
Any future changes to the ISIC Archive will not affect the versions of the data available at the above links. The metadata on the ISIC Archive propper are subject to change. The training data reflected currently in the ISIC Archive propper are available at https://api.isic-archive.com/collections/390/.
Name | Affiliation |
---|---|
Veronica Rotemberg, M.D., Ph.D. | Memorial Sloan Kettering Cancer Center, New York City, NY, USA) |
Nicholas Kurtansky | Memorial Sloan Kettering Cancer Center, New York City, NY, USA |
Name | Affiliation |
---|---|
Jochen Weber | Memorial Sloan Kettering Cancer Center |
Kivanc Kose, Ph.D. | Memorial Sloan Kettering Cancer Center |
Allan Halpern, M.D. | Memorial Sloan Kettering Cancer Center |
Maura Gillis | Memorial Sloan Kettering Cancer Center |
Josep Malvehy, M.D. | Hospital Clinic de Barcelona |
H Peter Soyer, Prof., M.D. | the University of Queensland |
Harald Kittler, Prof., M.D. | Medical University of Vienna |
Konstantinos Liopyris, M.D. | University of Athens |
Linda K Martin, M.D. | Melanoma Institute Australia |
Pascale Guitera, M.D. | Melanoma Institute Australia |
Alexander A Navarini, Prof., M.D. | University Hospital of Basel |
Victoria J Mar, M.D. | Alfred Hospital |
Vin Rajeswaran, M.D. | FNQH Cairns |
Noel Codella, Ph.D. | Microsoft |